Counterfactual Multi-Agent Policy Gradients

Understand

Cooperative multi-agent systems can be naturally used to model many real world problems, such as network packet routing and the coordination of autonomous vehicles.

• There is a great need for new reinforcement learning methods that can efficiently learn decentralised policies for such systems.
• To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients.
• COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies.